News for hackers. Stuff that matters.
Re:Tesla Model 3 Drives into Overturned Truck in Apparent Au... by SomewhatLikely on Monday June 01, 2020 @07:59PM (#23385578)
Doesn't seem like it was necessary here. I'm no computer vision expert, but surely parallax between multiple cameras and/or multiple time points would make detecting such a massive object simple.
Re:Tesla Model 3 Drives into Overturned Truck in Apparent Au... by MauranKilom on Monday June 01, 2020 @08:03PM (#23385602)
Large uniform/featureless surfaces are the bane of stereo vision. And propagating in from the borders is extremely risky if there's any occlusion affecting the borders (read: if you get the borders wrong).

Maybe in this particular instance you could look at the data and go "yep, that white surface is indeed closing in and not just some part of the sky". But how many false positives do you allow for "there's a huge thing in my way that requires emergency braking" in interstate scenarios?

Re:Tesla Model 3 Drives into Overturned Truck in Apparent Au... by screye on Monday June 01, 2020 @08:17PM (#23385687)
This actually seemed like an adversarial case.

It seems like the color of the truck and that of the road were near identical to each other. Maybe no different that what it looks like when the road changes textures to a worse surface or or hits an odd pot hole.

It is likely the car alerted the owner to take over, but did not brake on its own.

The thing about LIDAR is detecting objects becomes shit easy. One thing is for sure. I can guarantee such an accident would not have happened with LIDAR.

Re:Tesla Model 3 Drives into Overturned Truck in Apparent Au... by aeternum on Monday June 01, 2020 @08:56PM (#23385984)
It's surprising they did not train for this given very similar accidents (hitting semi-trucks) in 2016 and 2019.

LIDAR isn't a surefire solve, it also has issues with large white surfaces and bright sunlight.